- Home
- Skills
- DevOps & Cloud
- Metasearch Aggregator
Works with the AI Agents you already use
Metasearch Aggregator
Run privacy-respecting meta-search through any SearXNG instance: spin one up with Docker, query its JSON API with curl and jq, filter by category and time range
Free
Metasearch Aggregator
Example session with this skill installed
Set up a local SearXNG instance and search for 'rust async runtime' across Google and DuckDuckGo, returning the top 5 results in JSON.
- Read your context and instructions
- Compiled the metasearch aggregator
SearXNG instance started on port 8888. Results:
- Tokio - https://tokio.rs (google)
- async-std - https://async.rs (ddg)
- Rust Async Book - https://rust-lang.github.io/async-book/ (google)
... [Total 5 items merged and deduplicated]
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Standard search APIs are often expensive, rate-limited, or compromise user privacy through tracking. Developers needing aggregated results from multiple engines currently have to manage multiple API keys and normalize varying data formats manually.
What it does
- Deploys a local SearXNG instance using Docker for private, self-hosted search.
- Queries the SearXNG JSON API using curl and jq for structured data retrieval.
- Aggregates and deduplicates results from Google, Bing, DuckDuckGo, and other engines into a single list.
- Filters search results by specific categories like news or science and recency time ranges.
- Handles engine-specific selection to compare rankings or source variety.
Frameworks & tools
Docker, SearXNG, curl, jq, and JSON API integration.
Why this beats prompting it yourself
Writing raw prompts for search often leads to hallucinated links or reliance on a single engine's bias. This skill provides the specific technical orchestration to stand up a metasearch aggregator and parse real-time, multi-engine data into clean JSON, ensuring you get actual live URLs rather than training-data guesses.
Use cases
- Build a privacy-first search tool that doesn't track user queries.
- Create a fallback search mechanism when primary search APIs are down.
- Generate automated reports by scraping and merging results from multiple search engines.
- Monitor recent news or scientific papers using specific category and time filters.
Known limitations
Does not support downloading or scraping heavy media like images and videos directly. Not suitable for searches requiring account-scoped personalization or private user data.
Does not support media scraping for images/videos. Requires Docker for local hosting or access to a public instance. Not for personalized/account-scoped search.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
3 uses
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 3 months ago
- Free with an Agensi account